From: Predicting high blood pressure using machine learning models in low- and middle-income countries
Variables \(\varvec{(\mu \pm \sigma )}\) | Total Population (n=184674) | Train dataset (n=147739) | Test Dataset (n=36935) |
---|---|---|---|
Age | 40.06 ± 13.27 | 40.08 ± 13.26 | 40.02 ± 13.31 |
Years at school | 7.6 ± 5.33 | 7.6 ± 5.33 | 7.58 ± 5.32 |
People in household | 3.01 ± 2.02 | 3.01 ± 2.02 | 3 ± 2.01 |
Earnings per year | 1727.08 ± 1533.97 | 1734.25 ± 1538.65 | 1698.52 ± 1515 |
Age started smoking | 18.65 ± 1.77 | 18.65 ± 1.77 | 18.63 ± 1.78 |
Length time smoking | 7.38 ± 6.32 | 7.34 ± 6.33 | 7.52 ± 6.28 |
Number tobacco | 7.62 ± 3.55 | 7.64 ± 3.47 | 7.57 ± 3.94 |
Age stopped smoking | 29.87 ± 5.81 | 29.87 ± 5.82 | 29.88 ± 5.77 |
Number alcoholic drinks | 4.76 ± 1.06 | 4.75 ± 1.06 | 4.76 ± 1.06 |
Number daily fruit vegetables | 10.91 ± 6.73 | 10.91 ± 6.72 | 10.91 ± 6.75 |
Days vigorous exercise | 4.66 ± 1.04 | 4.66 ± 1.04 | 4.67 ± 1.04 |
Days moderate exercise | 5.64 ± 1.41 | 5.64 ± 1.41 | 5.64 ± 1.41 |
Time walking bicycling minutes | 60.23 ± 34.33 | 60.33 ± 34.33 | 59.87 ± 34.32 |
Time sedentary | 206.03 ± 172.04 | 205.89 ± 171.9 | 206.57 ± 172.59 |
Height | 162.12 ± 10.29 | 162.12 ± 10.32 | 162.14 ± 10.17 |
Weight | 66.62 ± 17.73 | 66.63 ± 17.73 | 66.59 ± 17.7 |
Waist circumference | 84.89 ± 25.35 | 84.87 ± 25.13 | 84.98 ± 26.24 |
Hip circumference | 95.89 ± 15.71 | 95.88 ± 15.7 | 95.9 ± 15.75 |
Fasting blood glucose | 39.67 ± 37.09 | 39.6 ± 37.07 | 39.94 ± 37.17 |
Total cholesterol | 76.42 ± 72.24 | 76.26 ± 72.23 | 77.06 ± 72.29 |
Urinary sodium | 121.13 ± 32.8 | 121.09 ± 32.76 | 121.29 ± 32.95 |
Urinary creatinine | 55.04 ± 38.3 | 55.06 ± 38.39 | 54.96 ± 37.93 |
Triglycerides | 84.16 ± 23.99 | 84.13 ± 23.97 | 84.29 ± 24.08 |
Hdl cholesterol | 17.67 ± 17.64 | 17.62 ± 17.64 | 17.87 ± 17.65 |
Systolic | 126.91 ± 19.1 | 126.91 ± 19.09 | 126.89 ± 19.17 |
Diastolic | 80.27 ± 11.7 | 80.28 ± 11.7 | 80.22 ± 11.71 |
Reading bpm | 77.48 ± 12.32 | 77.48 ± 12.31 | 77.48 ± 12.33 |